File: src/voku/helper/data/utf8_fix.php

Recommend this page to a friend!
  Classes of Lars Moelleken  >  Portable UTF-8  >  src/voku/helper/data/utf8_fix.php  >  Download  
File: src/voku/helper/data/utf8_fix.php
Role: Auxiliary script
Content type: text/plain
Description: Auxiliary script
Class: Portable UTF-8
Manipulate UTF-8 text strings in pure PHP
Author: By
Last change: [+]: fix "UTF8::rawurldecode()" and "UTF8::urldecode()"

-> for non multi usage ...
[+]: optimize "UTF8::fix_simple_utf8()"
Date: 1 year ago
Size: 4,100 bytes
 

Contents

Class file image Download
<?php

// code source: https://github.com/devgeniem/wp-sanitize-accented-uploads/blob/master/plugin.php#L152
// table source: http://www.i18nqa.com/debug/utf8-debug.html

return [
   
// 3 char errors
   
'??' => '?',
   
'??' => '?',
   
'?' => '?',
   
'?' => '?',
   
'?' => '?',
   
'?' => '?',
   
'??' => '?',
   
'??' => '?',
   
'??' => '?',
   
'?' => '?',
   
'??' => '?',
   
'??' => '?',
   
'?' => '?',
   
'?' => '?',
   
'?' => '?',
   
// 2 char errors
   
"\xc2\x80" => "\xe2\x82\xac", // EURO SIGN
   
"\xc2\x82" => "\xe2\x80\x9a", // SINGLE LOW-9 QUOTATION MARK
   
"\xc2\x83" => "\xc6\x92", // LATIN SMALL LETTER F WITH HOOK
   
"\xc2\x84" => "\xe2\x80\x9e", // DOUBLE LOW-9 QUOTATION MARK
   
"\xc2\x85" => "\xe2\x80\xa6", // HORIZONTAL ELLIPSIS
   
"\xc2\x86" => "\xe2\x80\xa0", // DAGGER
   
"\xc2\x87" => "\xe2\x80\xa1", // DOUBLE DAGGER
   
"\xc2\x88" => "\xcb\x86", // MODIFIER LETTER CIRCUMFLEX ACCENT
   
"\xc2\x89" => "\xe2\x80\xb0", // PER MILLE SIGN
   
"\xc2\x8a" => "\xc5\xa0", // LATIN CAPITAL LETTER S WITH CARON
   
"\xc2\x8b" => "\xe2\x80\xb9", // SINGLE LEFT-POINTING ANGLE QUOTE
   
"\xc2\x8c" => "\xc5\x92", // LATIN CAPITAL LIGATURE OE
   
"\xc2\x8e" => "\xc5\xbd", // LATIN CAPITAL LETTER Z WITH CARON
   
"\xc2\x91" => "\xe2\x80\x98", // LEFT SINGLE QUOTATION MARK
   
"\xc2\x92" => "\xe2\x80\x99", // RIGHT SINGLE QUOTATION MARK
   
"\xc2\x93" => "\xe2\x80\x9c", // LEFT DOUBLE QUOTATION MARK
   
"\xc2\x94" => "\xe2\x80\x9d", // RIGHT DOUBLE QUOTATION MARK
   
"\xc2\x95" => "\xe2\x80\xa2", // BULLET
   
"\xc2\x96" => "\xe2\x80\x93", // EN DASH
   
"\xc2\x97" => "\xe2\x80\x94", // EM DASH
   
"\xc2\x98" => "\xcb\x9c", // SMALL TILDE
   
'?' => '',
   
'?' => '?',
   
'?' => '',
   
'?' => '',
   
'?' => '',
   
//'?' => '?', // duplicate key
   
'?' => '',
   
'?' => '',
   
'?' => '?',
   
'?' => '',
   
'?' => '',
   
'?' => '',
   
'?' => '',
   
'?' => '?',
   
'?' => '',
   
'Ž' => '?',
   
'?' => '',
   
'?' => '',
   
'?' => '',
   
'?' => '',
   
'?' => '?',
   
'?' => '',
   
'?' => '',
   
'?' => '',
   
'?' => '',
   
'?' => '?',
   
'?' => '',
   
'?' => '',
   
'š' => '?',
   
'?' => '',
   
'?' => '',
   
'?' => '?',
   
'?' => '',
   
'ž' => '?',
   
'?' => '',
   
'Ÿ' => '?',
   
'?' => '',
   
'¡' => '',
   
'á' => '',
   
'¢' => '',
   
'â' => '',
   
'£' => '',
   
'ã' => '',
   
'¤' => '',
   
'ä' => '',
   
'¥' => '',
   
'å' => '',
   
'¦' => '',
   
'æ' => '',
   
'§' => '',
   
'ç' => '',
   
'¨' => '',
   
'è' => '',
   
'©' => '',
   
'é' => '',
   
'ª' => '',
   
'ê' => '',
   
'«' => '',
   
'ë' => '',
   
'¬' => '',
   
'ì' => '',
   
'®' => '',
   
'î' => '',
   
'¯' => '',
   
'ï' => '',
   
'°' => '',
   
'ð' => '',
   
'±' => '',
   
'ñ' => '',
   
'²' => '',
   
'ò' => '',
   
'³' => '',
   
'ó' => '',
   
'´' => '',
   
'ô' => '',
   
'µ' => '',
   
'õ' => '',
   
'¶' => '',
   
'ö' => '',
   
'·' => '',
   
'÷' => '',
   
'¸' => '',
   
'ø' => '',
   
'¹' => '',
   
'ù' => '',
   
'º' => '',
   
'ú' => '',
   
'»' => '',
   
'û' => '',
   
'¼' => '',
   
'ü' => '',
   
'½' => '',
   
'ý' => '',
   
'¾' => '',
   
'þ' => '',
   
'¿' => '',
   
'ÿ' => '',
   
'?' => '',
   
// 1 char errors last (don't use them)
    //'' => '',
    //'' => '?',
    //'' => '',
    //'' => '',
    //'' => '',
    //'' => '',
    //'' => '',
    //'' => '',
];


For more information send a message to info at phpclasses dot org.